Optimizing job scheduling on cloud resources using the first-come, first-served-SlotFree method

Abstract

Cloud computing environments encounter significant challenges in job scheduling, particularly due to excessive waiting times and inefficient resource utilization associated with conventional algorithms such as first-come, first-served (FCFS) and backfilling. This study introduces FCFS-SlotFree, a novel scheduling algorithm that enhances resource allocation efficiency by dynamically sorting jobs based on their arrival times and workloads, and subsequently assigning them to a fixed set of virtual machines (VMs) without relying on rigid time-slot constraints. This flexible scheduling approach facilitates better adaptation to heterogeneous workloads. Extensive experiments conducted under realistic cloud scenarios demonstrate that FCFS-SlotFree significantly reduces average waiting time (AWT) by approximately 32.78% compared to FCFS and by 9.68% compared to backfilling, while concurrently improving resource utilization by 3.58% and 1.27%, respectively. The results substantiate the algorithm’s effectiveness in optimizing scheduling performance and resource efficiency within complex cloud environments.